collaborators

8 papers

cs.CV2026

DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration

Jinzhou Tang, Fan Feng, Minghao Fu +3

Learned world models excel at interpolative generalization but fail at extrapolative generalization to novel physical properties. This limitation arises because they learn statisti…

cs.CV2026

Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities

Shanshan Zhao, Xinjie Zhang, Jintao Guo +9

Recent years have seen remarkable progress in both multimodal understanding models and image generation models. Despite their respective successes, these two domains have evolved i…

cs.CV2025

Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models

Minghao Fu, Guo-Hua Wang, Tianyu Cui +4

Text-to-image diffusion models deliver high-quality images, yet aligning them with human preferences remains challenging. We revisit diffusion-based Direct Preference Optimization…

cs.CV2025

Ovis-Image Technical Report

Guo-Hua Wang, Liangfu Cao, Tianyu Cui +8

We introduce , a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational c…

cs.SD2025

Benchmarking Sub-Genre Classification For Mainstage Dance Music

Hongzhi Shu, Xinglin Li, Hongyu Jiang +2

Music classification, a cornerstone of music information retrieval, supports a wide array of applications. To address the lack of comprehensive datasets and effective methods for s…

cs.CV2025

TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance

Minghao Fu, Guo-Hua Wang, Xiaohao Chen +4

Recent advances in text-to-image synthesis largely benefit from sophisticated sampling strategies and classifier-free guidance (CFG) to ensure high-quality generation. However, CFG…